from transformers import AutoProcessor, Data2VecAudioForCTC
import torch
from datasets import load_dataset, Audio

dataset = load_dataset("mozilla-foundation/common_voice_11_0", "uk", split="test")
# Resample
dataset = dataset.cast_column("audio", Audio(sampling_rate=16_000))

processor = AutoProcessor.from_pretrained("Respeecher/ukrainian-data2vec-asr")
model = Data2VecAudioForCTC.from_pretrained("Respeecher/ukrainian-data2vec-asr")
model.eval()

sampling_rate = dataset.features["audio"].sampling_rate
inputs = processor(dataset[1]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits
predicted_ids = torch.argmax(logits, dim=-1)

transcription = processor.batch_decode(predicted_ids)
transcription[0]

Training Details

Training code and instructions are available on our github